Artificial intelligence still has some way to go

is there even any legal requirement to disclose what goes into a model? if someone builds their own private model entirely off of copyrighted material, how would anyone even know based on the outputs?

This is not unlike imagining if someone built a massive library of microscopic samples from famous songs and then used those to make new music in which the source samples were entirely unrecognizable. There wouldn't be rights issues raised because the end result is completely different from the inputs. (Yes, I understand that AI image engines do not actually piece together elements of existing images)

I'm somewhat open to the idea that people can opt their images out of publicly available models, even though I don't exactly buy that putting them in there causes harm in any obvious way that taking them out would somehow fix.

serious question for those who actually think AGI is gonna be able to self-replicate and produce world-ending superintelligence within 5 minutes or whatever - what is this going to run on? wouldn't this sort of thing just instantly overload whatever CPU it was running on?

something something nvidia stock price

It's surprising how recognizable even micro-samples are (and apparently AI is being used for sample-snitching now). And "There wouldn't be rights issues raised because the end result is completely different from the inputs." -- there definitely are if the sample is identified and the end result has made a lot of money, it doesn't matter if it's a one-shot.

I don't know how good they've gotten at recognizing all samples, and I also don't know how far they would plan to take sample litigation. Sampling is massively widespread and most of it happens without issues. My example specified that the samples in the context of the new piece of music were unrecognizable. Perhaps at this point that is a purely hypothetical idea because technology has gotten so good at recognizing samples, so let's assume I mean unrecognizable by human ears. In my experience, not a lot music gets targeted for sample violation unless the samples are fairly discernable and have an active role in the music, but perhaps that has changed.

Either way, AI images are not in fact made up of samples of other images so not sure it's relevant at all. My only point was, if the inputs are not discernable in the outputs, how is someone even going to go about proving harm?

Right, the fact that it's going to be impossible to prove is all the more reason that opt-outs need to be put in place now, imo.

(the sample issue is an aside, but micro-chops that you'd think would be unrecognizable to the human ear are often not, people are surprisingly good at that kind of pattern recognition even if it's been re-pitched. There are tons of Dilla and Daft Punk samples that have been identified that are just split seconds of sound, not to mention drum hits. Of course if something has been completely mangled with effects to sound totally different then it's probably impossible, but usually the point of sampling is because there's some sort of valuable quality in the source material you want to maintain?)

yes, microsamples are now recognizable, but I was indeed thinking of samples that had been mangled beyond all recognition, which absolutely happens all the time, granular synthesis being one prominent example.

I don't know how far litigation has been taken with stuff like microsamples, are there cases of musicians being successfully sued for barely discernable or entirely unrecognizable samples? My totally non-professional understanding of the laws around sample clearance led me to believe that the mere presence of an uncleared sample in a piece of music isn't necessarily enough to hold a musician liable. I'm under the impression that the length of the sample, how central it is to the piece of music, and the financial losses incurred by the original artist are all taken into account.

My understanding is that the whole "it's fine if it's under X seconds" thing is a myth.

This article talks about an NWA example: https://www.wipo.int/wipo_magazine/en/2009/06/article_0006.html

I don't know of a lawsuit example around true micro-samples, but I'm sure it could happen if the sampling track was a big enough hit, especially these days.

this is exactly why I avoid recording anything good enough to be a big hit

My outlook on copyright infringement litigation for music, especially samples in music, is that it has gone way overboard for decades, so I hope new technology does not mean it will start to ramp up further. I get the sense that people coming up today, possibly inspired by the AI discourse, have a much more welcoming attitude towards suing musicians for this stuff, but hopefully I'm wrong.

I think with actual AI data sets, lawsuits are going to be much more difficult for individuals since there isn't any way to use something generated through AI to identify what specific items were in the model and which ones helped determine the thing that was generated.

As much as I don't love the practice, it's hard for me to see how you could draw a legal distinction between training an AI on a bunch of music and the normal process by which a human writes music in part by synthesizing ideas from music they've listened to. If I could write a "Drake-style" song but wasn't impersonating Drake, sampling Drake, or borrowing any specific copyrightable elements in my song, the mere fact that I could ingest and spit back out his style would not make me a copyright infringer. So if AI does the same, I don't see the claim.

I think the "wasn't impersonating Drake" part could end up being more of a sticking point with this tech? but honestly I agree with the general idea here that copyright isn't a very good legal framework for analyzing this stuff (my preference would be more serious consideration of the idea of the commons, but that's fairly idealistic). Still, I also think "let the AI companies do whatever they want" isn't a good approach either; I don't know how much longer these tools will remain free to use

some of the most popular image tools are not free to use right now

it's hard for me to see how you could draw a legal distinction between training an AI on a bunch of music and the normal process by which a human writes music in part by synthesizing ideas from music they've listened to.

I'm somewhat sympathetic to this argument, but since AI can ingest and spit out music at an incredible rate compared to a human, it doesn't feel equivalent. And since this is likely to lead to devaluing human-made music (at least in certain areas, like commercial and soundtrack music) even more than it's already be devalued, maybe not?

ya for instance I think Utopia's "Deface the Music" is fair game and shouldn't have to pay any royalties but if you prompted an AI to write a bunch of "Beatles-like" songs and released the result that should not be kosher

I'm somewhat sympathetic to this argument, but since AI can ingest and spit out music at an incredible rate compared to a human, it doesn't feel equivalent. And since this is likely to lead to devaluing human-made music (at least in certain areas, like commercial and soundtrack music) even more than it's already be devalued, maybe not?

― Random Restaurateur (Jordan), Monday, June 5, 2023 3:01 PM (eight minutes ago) bookmarkflaglink

I mean yeah but there's really nothing in the current legal framework to deal with this. And it's also hard to conceive of how you would compensate musicians for it.

which isn't to say people shouldn't try to come up with something, I just don't think any existing royalty type framework is usable

sounds like something for actual legal experts to parse and negotiate

or perhaps a lawyer AI

Yeah, idk how royalties would work, maybe it depends on the size of the training set (ie you get basically nothing if you're part of a massive training set, but you get something if an AI is trying to copy a more narrow set of artists?). I'd gladly take an opt-in structure where the burden is on AI companies to get consent, and get a big ol' fine if they're found to have skipped that bit.

I liked this piece:

wrote about AI turning everyone into 'creators' and the end of endings https://t.co/ZXzPwxu01m pic.twitter.com/T3WRIYrFRf

— Charlie Warzel (@cwarzel) June 6, 2023

Uh oh, Alison Goldfrapp is part of the AI hivemind.

https://www.youtube.com/watch?v=qYkFBecIGRo

lol

https://venturebeat.com/ai/senators-send-letter-questioning-mark-zuckerberg-over-metas-llama-leak/

https://www.washingtonpost.com/technology/2023/06/05/chatgpt-hidden-cost-gpu-compute/

article goes all over the place. it’s good to raise the issue that there’s a huge resource cost to these things and a ton of physical devices behind the scenes, but I also read this and thought “great, the completely imaginary nvidia stock market shenanigans are going to be worse now”

article goes all over the place. it’s good to raise the issue that there’s a huge resource cost to these things and a ton of physical devices behind the scenes, but I also read this and thought “great, the completely imaginary nvidia stock market shenanigans are going to be worse now”

― mh, Wednesday, June 7, 2023 6:48 PM (yesterday) bookmarkflaglink

It’s also _rapidly_ changing. This is why I’m surprised by NVIDIA’s success. Yes, everyone is buying A100s as fast as they can be built (myself included), but everyone is also actively jumping ship. Google, Meta, and Microsoft already fabricate their own devices that use a fraction of the energy than GPUs.

I also don’t think many people know about advances in optical computing. It’s entirely possible to build _entirely passive_ accelerators. I don’t think we’ll see entirely passive devices ship to consumers but I’d bet anything we’ll see optical-electrical accelerators in popular consumer devices in a few years that use very little energy (and certainly wouldn’t increase existing energy consumption).

I'm skeptical that AI can do anything better than our natural intelligence. We don't understand our intelligence enough. We don't understand the brain enough, our bodies etc.

We don't have to get mired in that question to be excited about what we as centaurs could do

— Holly Herndon (@hollyherndon) June 7, 2023

I touched one of the machine with 8 A100s in it a couple weeks ago!

NVidia's thrown so much money into marketing and supporting software libraries and frameworks to lock people into their ecosystem and to my understanding, a bunch of things people are doing aren't even necessarily a great fit for the hardware. I've gotten the impression they're doing the best to provide free or incentivized resources up and down the academic and research pipeline to further lock people into CUDA, etc.

I haven't read up on the optical computing field but that sounds promising.

xp oof

Oh, your natural intelligence is as an object rotator? I'm a protein folder. I'm just built different

I’m sure nvidia is going to be developing specialized AI chips going forward, and they have some of the best chip engineers in the world no?

I cursed myself by posting about this because a meeting mere minutes ago devolved into a tangent about all the different companies trying to entice my coworkers on to different compute platforms

but the kicker is the ones specifically pitching themselves not as compute platforms, but as domain-specific solutions

with the caveat that I'm definitely not in the pharmaceutical space, this is the kind of thing nvidia is pitching:
https://www.nvidia.com/en-us/gpu-cloud/bionemo/

ai is good again for the very first time

...I have just heard of the Knot In My Name campaign.

You know how AI scrapes sites like AO3 for machine training? The idea is to flood AO3 with omegaverse to the point that all AI text generators everywhere will default to fated mates, breeding, and of course knotting.

— KJ Charles (@kj_charles) June 9, 2023

I dont understand a word of that, EILI5?

I think they want to poison AI with erotic fanfic.

ChatGPT giving you all the details of the Hogwarts 20th Reunion gangbang and barbecue

I feel like another internet exists that I've no clue about, I swear.

it does, you are not wrong

I don't really read fanfic but I do like to read *about* fanfic - it's a fascinating subculture with even more fascinating and often hilarious sub-subcultures.

* AO3 is Archive Of Our Own, which is currently the most popular site to post/read fanfic.

* The omegaverse is a type of fanfic based on the concept of alphas, betas and omegas. It's an animalistic sex thing, where your characters have heat cycles and have to mate according to dominance hierarchies and biological compulsion. Honestly, I find the whole thing pretty icky but it is very popular.

I could extrapolate what the specific acts are from my basic knowledge, but I don't actually know for sure so those things shall have to remain mysterious.

I’ve read fic on and off since my teens and omegaverse is just really disgusting to me. It’s popular but also wildly disputed. Like a lot of terrible fic trends, I think it originated from the Supernatural fandom.

Ohhh, ha, I was wondering if it maybe came from Twilight fandom and werewolves. I did read about someone trying to claim ownership of it and suing other omegaverse authors, but I couldn't remember what fandom she was part of (and she almost certainly wasn't the inventor of it anyway).

oops

https://apnews.com/article/artificial-intelligence-chatgpt-courts-e15023d7e6fdf4f099aa122437dbb59b

The omegaverse is a type of fanfic based on the concept of alphas, betas and omegas. It's an animalistic sex thing, where your characters have heat cycles and have to mate according to dominance hierarchies and biological compulsion. Honestly, I find the whole thing pretty icky but it is very popular.

They have to? So strange.

In any case it is impossible to screw up chat gpt by training it on weird and misleading content. In order for it to work at all it has to have absorbed a dizzying amount of content. Anything you throw at it will just be a blip that it ignores.

Airborne for The #AISummit #London.🇹🇼🇬🇧

Catching up on email in airplane mode is a breeze.✈️

Blessings for the amazing work of @ggerganov on state-of-the-art open models running via laptop.🙏

Let’s #FreeTheFuture🖖 — together! pic.twitter.com/QTB0rcUvcW

— Audrey Tang 唐鳳 (@audreyt) June 11, 2023

this strikes me as one version of the future — taiwan's inimitable and extraordinary Audrey Tang (Minister of Digital Affairs - also a poet) running what looks like a perpetual & personalized AI assistant, which can compose emails for them according to a bunch of precedents. Tang releases public transcripts of almost all their official talks (and even sit-down meetings i think), so presumably their AI is loaded with tons of data.

I wish I could unlearn what omegaverse is but I am utterly unsurprised it comes from Supernatural fanfic.

i got interesting in online publishing platforms a few months ago and came across this website with a whole suite of tools and a quite fleshed out system for monetizing, all very professionally done and i was like huh, never heard of this, looks like a really engaged community and.... it was literally thousands of omegaverse short stories and novels. with a handful of 'i fell in love with my bully' YA serializations. this is the future of fiction, people

interestED

if you want a vision of the future, imagine an ai writing omegaverse fics on a human device- forever

i expect fully a half of those authors are using at least partially ai-generated copy

I've been occasionally trying to devise creative ways to test "Is this think 'thinking' in some sense or is it just spitting out text?"

My latest idea was to see what happens if I ask GPT to start a conversation and then plug the prompt into Bard, then plug Bard's response back into GPT, and so on. It started off ok - I asked GPT to start a conversation, and it responded "Absolutely! Here's a conversation starter: "What is one book that significantly impacted your life, and how did it change your perspective?"

Bard gave me a relatively long and sophisticated (if insipid) response about The Alchemist by Paulo Coelho. I plugged that back into GPT, and it in turn responded in a relatively sophisticated (but again insipid) way, and this continued back and forth for a handful of exchanges. Eventually, things started to crack slightly though.

First, Bard asked GPT: "I would love to hear about your own writing journey and learn from your experiences."

GPT then responded with one of its stock "As an AI language model..." type responses, followed by what was pretty clearly a conversation ender:

As an AI developed by OpenAI, I don't have personal experiences or a writing journey of my own. However, I'm here to provide insights based on a vast range of data I've been trained on.

If you have any other questions about writing, need suggestions for more writing resources, or want feedback on certain writing-related topics, feel free to ask! I'm here to help. Keep nurturing your passion for writing, and remember that every word you write brings you one step closer to becoming the writer you aspire to be. I wish you all the best in your writing endeavors!

Bard did not seem to pick up on any of this, and also began referring, confusingly, to its interlocutor as "Bard."

Following that, the conversation devolved into a tennis match of long goodbyes, each basically just restating the same platitudes in different words. I played out this exchange a bunch of times just to see if either AI would ever change its response, and it seems the answer is no, it just gets stuck in this endless feedback loop of empty positivity.

If either GPT or Bard were "thinking" in any meta sense, rather than just generating prompt responses, it seems unlikely that this would happen. This made me pretty skeptical of these "emergent abilities" and "sparks of AGI" claims.

Entire conversation here:

https://chat.openai.com/share/0f1f55fc-25ae-44e9-b53f-fec544d0e001